Perplexity 开源 pplx-embed-v2-late：9B/0.6B 多模态嵌入模型
Perplexity 把两个嵌入模型开源了，9B 做索引、0.6B 能跑在手机上，PDF 不用 OCR 直接搜，成绩还挺好。
Perplexity 开源了 pplx-embed-v2-late，包含 9B 和 0.6B 两个 late-interaction 多向量嵌入模型，共享同一嵌入空间，支持文本、图像和 PDF 页面检索，无需 OCR。9B 用于服务端索引多模态数据，0.6B 可在设备端做查询。两个模型在 MADQA 上得 92.4%，在 BrowseComp+ 上得 64%，权重已发布在 Hugging Face。
We’re open-sourcing pplx-embed-v2-late, multi-vector embeddings for text and images, 9B and 0.6B, in one shared embedding space. You can use these to index multimodal data with 9B, and query on device with 0.6B. This also enables you to search over PDF pages with no OCR. And scores 92.4% on MADQA, 64% on BrowseComp+. Weights available on @huggingface now. Perplexity @perplexity_ai We're releasing pplx-embed-v2-late, two late-interaction embedding models that retrieve text, images, and pages with a shared embedding space for cross-model querying. Both models achieve frontier performance and are publicly available on Hugging Face. perplexity.ai/hub/blog/multi… 🔗 View Quoted Tweet 💬 29 🔄 6 ❤️ 106 👀 7284 📊 27 ⚡
